Back to all available

Securing federated learning: A comprehensive survey on privacy challenges and solutions in medical image analysis

artificial-intelligence
computer-vision
security-and-privacy

Abstract

This paper provides a comprehensive survey of safety and privacy issues related to Federated Learning (FL) in medical image analysis. FL facilitates joint model training among multiple healthcare institutions without compromising sensitive patient information. However, it is susceptible to various threats, including data poisoning, Byzantine attacks, and inference attacks. We systematically categorize these threats and identify two key vulnerable assets: medical data and model parameters. We also explore counter-threat strategies, including cryptographic methods, secure aggregation, perturbation techniques, and various security protocols, to safeguard patient information and ensure model integrity. The role and impact of FL in medical imaging applications are investigated, emphasizing its ability to protect patient privacy while potentially improving diagnostic accuracy. In this survey, we examine challenges such as data heterogeneity, communication overhead, and standardization issues, and discuss potential future research directions to tackle these challenges. This extensive research serves as a comprehensive reference for researchers and practitioners striving to develop secure, privacy-preserving FL systems in healthcare, aiming to enhance the efficacy of medical decision-making.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].